© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 12224
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Grover"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Grove" or related prominent figures associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.74
     EPS
    -0.67
     writ
    -0.63
     nested
    -0.62
    aeda
    -0.61
     CPC
    -0.61
     apr
    -0.60
     christ
    -0.59
     Eug
    -0.58
     Bayer
    -0.58
    POSITIVE LOGITS
    tesque
    1.13
    cery
    1.11
    lean
    1.08
    ovy
    0.99
    ove
    0.96
    bie
    0.95
    bies
    0.93
    bys
    0.92
    vernment
    0.85
    gan
    0.84
    Activations Density 0.023%

    No Known Activations